Knowledge catalogue
arXiv:2508.00414v3 Announce Type: replace Abstract: General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reason
arXiv:2604.20720v1 Announce Type: cross Abstract: Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performa
arXiv:2604.20358v1 Announce Type: new Abstract: The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on exp
arXiv:2604.20658v1 Announce Type: new Abstract: Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-solvin
arXiv:2505.14984v2 Announce Type: replace Abstract: Open-Domain Table Question Answering (TQA) involves retrieving relevant tables from a large corpus to answer natural language queries. Traditional d
CrowdStrike Holdings Inc. today announced the launch of Project QuiltWorks, an industry coalition aimed at helping enterprises find and fix the wave of software vulnerabilities being surfaced by front
arXiv:2604.20389v1 Announce Type: cross Abstract: The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against
Databricks has announced a partnership with OpenAI to integrate GPT-5.5, OpenAI's latest language model, into its data and AI platform. This collaboration enables Databricks customers to leverage GPT-
Day 0 vLLM support for Qwen3.6-27B! @vllm_project ♥️❤️ 🎉 Day-0 vLLM support for Qwen3.6-27B! Congrats to @Alibaba_Qwen on the new 27B dense model release. Looking forward to more of the Qwen3.6 series
At Google Cloud, every day is Developer Day, but none so much as day 2 of Google Cloud Next, when we hold the developer keynote. This year’s topic? An in-depth look at Gemini Enterprise Agent Platform
Vercel announced support for DeepSeek V4 model through its AI Gateway service, enabling developers to access this AI model alongside other supported models on the platform. This addition expands Verce
arXiv:2604.19776v1 Announce Type: new Abstract: Tuberculosis (TB) is one of the world's deadliest infectious diseases, and in South Africa, it contributes a significant burden to the country's health
arXiv:2604.20443v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been shown to possess Theory of Mind (ToM) abilities. However, it remains unclear whether this stems from robust rea
arXiv:2604.20098v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications. Conformal Prediction (CP) addresses this by ca
arXiv:2604.19966v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in settings where sensitivity to low-level image degradations matters, including content moderatio
arXiv:2604.19781v1 Announce Type: cross Abstract: Automated scoring of student work at scale requires balancing accuracy against cost and latency. In 'cascade' systems, small language models (LMs) han
'don't retweet this, don't retweet this, don't retweet this...' ah fuck it, life imitates art. In Vending-Bench Arena (the multiplayer version of Vending-Bench with competition dynamics), GPT-5.5 actu
arXiv:2604.20306v1 Announce Type: cross Abstract: Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However,
arXiv:2604.20168v1 Announce Type: new Abstract: This paper presents the Duluth approach to SemEval-2026 Task 6 on CLARITY: Unmasking Political Question Evasions. We address Task 1 (clarity-level class
arXiv:2604.20523v1 Announce Type: cross Abstract: We study whether Large Language Models (LLMs) can perform feature model analysis operations (AOs) directly on semi-formal textual blueprints, i.e., co
Earth Day at #GoogleCloudNext, I’m demoing a Sustainability Agent at the @nvidia booth. Built with @Google ADK, @googlegemma, #nemotron, Cloud Run, @milvusio , @LangChain & @ollama to reason across im
arXiv:2511.06209v4 Announce Type: replace Abstract: LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve LLM performance by samplin
embers GPT-5.5, not fully saturating the TikZ unicorn test yet but getting awfully close ... (yes this is actual TikZ code, I personally find it so unbelievable that I'm putting the code below for any
arXiv:2508.17761v3 Announce Type: replace Abstract: In safety-critical applications data-driven models must not only be accurate but also provide reliable uncertainty estimates. This property, commonl
arXiv:2604.20544v1 Announce Type: cross Abstract: The efficacy of Large Vision-Language Models (LVLMs) is critically dependent on the quality of their training data, requiring a precise balance betwee
arXiv:2604.19762v1 Announce Type: new Abstract: The Voynich Manuscript (VMS) exhibits a script of uncertain origin whose grapheme sequences have resisted linguistic analysis. We present a systematic a
arXiv:2604.19761v1 Announce Type: new Abstract: Modern machine learning is still largely organized around a single recipe: choose a parameterized model family and optimize its weights. Although highly
arXiv:2604.19835v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters f
arXiv:2604.20726v1 Announce Type: cross Abstract: This work explores the role of prompt design and judge selection in LLM-as-a-Judge evaluations of free text legal question answering. We examine wheth
arXiv:2604.19754v1 Announce Type: new Abstract: Automated scoring of students' scientific explanations offers the potential for immediate, accurate feedback, yet class imbalance in rubric categories p
arXiv:2604.20570v1 Announce Type: new Abstract: Spatial intelligence is essential for multimodal large language models, yet current benchmarks largely assess it only from an understanding perspective.
LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, us
arXiv:2411.00585v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have become foundational in modern language-driven software applications, profoundly influencing daily life. A cr
SpaceX's Falcon 9 rocket successfully launched 24 Starlink satellites from a California launch facility, continuing the company's ongoing deployment of its satellite internet constellation. This missi
arXiv:2604.20735v1 Announce Type: new Abstract: Accurate condition monitoring of industrial equipment requires inferring latent degradation parameters from indirect sensor measurements under uncertain
arXiv:2604.20429v1 Announce Type: new Abstract: Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and com
arXiv:2506.21095v4 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative training while preserving privacy, yet it introduces a critical challenge: the 'illusion of fair
arXiv:2604.20736v1 Announce Type: new Abstract: Semi-supervised node classification is a foundational task in graph machine learning, yet state-of-the-art Graph Neural Networks (GNNs) are hindered by
arXiv:2604.20462v1 Announce Type: cross Abstract: Behaviour-Driven Development (BDD) suites accumulate step-text duplication whose maintenance cost is established in prior work. Existing detection tec
arXiv:2407.09577v4 Announce Type: replace Abstract: Normalization layers are ubiquitous in large language models (LLMs) yet represent a compute bottleneck: on hardware with distinct vector and matrix
arXiv:2512.15808v2 Announce Type: replace-cross Abstract: Foundation models (FMs) are driving a prominent shift in biomedical imaging from task-specific models to unified backbone models for diverse t
arXiv:2604.19789v1 Announce Type: new Abstract: We present an autonomous large language model (LLM) agent for end-to-end, data-driven materials theory development. The model can choose an equation for
arXiv:2604.20006v1 Announce Type: new Abstract: Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. Ho
arXiv:2604.20191v1 Announce Type: cross Abstract: Interpretable driver attention prediction is crucial for human-like autonomous driving. However, existing datasets provide only scene-level global gaz
arXiv:2604.20822v1 Announce Type: new Abstract: The offshore wind energy sector is expanding rapidly, increasing the need for independent, high-temporal-resolution monitoring of infrastructure deploym
OpenAI's GPT-5.5 Bio Bug Bounty program invites security researchers to identify and report vulnerabilities in GPT-5.5's biological information handling capabilities, focusing on potential misuse risk
GPT-5.5 in Codex is a delight to work with: - Super sharp with responses - It understands intent better than any model - Great 'personality' - Gets lots of stuff done without pausing unnecessarily It
I don't have verified information about a GPT-5.5 model release. This appears to be either a fictional or future-dated post, as it references a non-existent model and uses a URL format/status ID that
GPT-5.5 is likely the best model in the world. But open models like Kimi and Minimax get almost identical coding benchmark scores at 10-25x lower cost. I broke down the benchmarks and pricing. Here's
GPT-5.5 is now accessible in Hermes Agent through the ChatGPT/Codex OAuth provider. Run `hermes update` to access now or learn how to get started with Hermes Agent here: https://hermes-agent.nousresea
Carl Franzen / VentureBeat: GPT-5.5 is priced at 5/1M input tokens and 30/1M output tokens, double GPT-5.4's pricing; GPT-5.5 Pro costs 30/1M input tokens and 180/1M output tokens — After months of ru
The Verge: GPT-5.5 is rolling out to Plus, Pro, Business, and Enterprise users in ChatGPT and Codex, and GPT-5.5 Pro to Pro, Business, and Enterprise users in ChatGPT — The new model ‘excels’ at tasks
GPT-5.5 may not be in the official OpenAI API... but it's available via the apparently approved-of Codex API backdoor So I used that to make these pelicans (default and xhigh)! https://simonwillison.n
GPT-5.5 achieved state-of-the-art performance on the ARC-AGI-2 benchmark, with scores ranging from 85.0% on maximum difficulty tasks to 33% on low difficulty tasks. The model demonstrated consistent i
arXiv:2604.19840v1 Announce Type: new Abstract: Graph-theoretic approaches offer simplicity, interpretability, and low computational cost for molecular property prediction. Among these, the model prop
Here’s my view on GPT-5.5, which I have been testing for a couple of weeks. It conducted not-bad social science research on its own, developed a novel RPG & more. There is still jaggedness but GPT-5.5
arXiv:2604.20140v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex
How close are models to building a perfect Slack clone with less than 50,000 of tokens? I feel like not that far... Claude Code spend had gotten to 10.95M runrate peak at SemiAnalysis But then Opus 4.
arXiv:2604.19783v1 Announce Type: new Abstract: Which persuasion strategies, if any, are associated with donation compliance? Answering this requires fine-grained strategy labels across a full corpus
arXiv:2604.19770v1 Announce Type: new Abstract: We present a hybrid multi-phase page matching algorithm for automated comparison of Japanese building permit document sets. Building permit review in Ja